Cyberax AI Playbook
cyberax.com
← All models
Model · OpenAI · Speech-To-Text

Whisper large-v2

OpenAI's previous-generation flagship speech-to-text model. Superseded by Whisper large-v3 — kept here for lineage and any teams still pinned to v2.

Modality
Speech-To-Text
License
MIT (Open)
Released
December 6, 2022
Last verified
May 10, 2026
Runs locally
Yes

Try it

WhereTypeNotes
Hugging Face weights Open weights, MIT

Version history

  1. Whisper large-v3 Turbo Oct 2024
  2. Whisper large-v3 Nov 2023
  3. Whisper large-v2 Dec 2022 Current Deprecated

Change log

  • — Backfilled lineage entry; v3 has been the recommended Whisper since 2023.

Related models

GPT Live Transcribe

OpenAI · Speech-To-Text

OpenAI's realtime transcription model — the streaming half of the pair replacing GPT-4o Transcribe. Built for live captioning and voice agents, with tunable latency and keyword hints.

Proprietary
Try on: OpenAI API
Released Jul 2026 · Verified 2026-10-28

GPT Transcribe

OpenAI · Speech-To-Text

OpenAI's current hosted transcription model and the named replacement for GPT-4o Transcribe. Priced per minute of audio rather than per token, for batch and file-based transcription.

Proprietary
Try on: OpenAI API
Released Jul 2026 · Verified 2026-10-28

Voxtral Mini 4B Realtime

Mistral AI · Speech-To-Text

Mistral's open live-transcription model. It writes text as people speak, under half a second behind, in 13 languages — accuracy close to offline transcribers, small enough to run on one graphics card.

Apache 2.0 Open Runs locally Mac · 8 GB+
Try on: Hugging Face · Mistral API
Released Feb 2026 · Verified 2026-10-28

Qwen3-ASR

Alibaba · Speech-To-Text

Alibaba's open speech-recognition family. The 1.7B model transcribes 30 languages and 22 Chinese dialects and detects the language itself; a separate ForcedAligner-0.6B adds word-level timestamps.

Apache 2.0 Open Runs locally Mac · 8 GB+
Try on: Hugging Face · GitHub (qwen-asr package)
Released Jan 2026 · Verified 2026-10-28

VibeVoice-ASR

Microsoft · Speech-To-Text

Microsoft's open long-form transcription model. It takes up to an hour of audio in one pass and returns who spoke, when, and what they said — transcription, speaker labels and timestamps together, in 50+ languages.

MIT Open Runs locally Mac (slow) · 24 GB+
Try on: Hugging Face · GitHub · VibeASR.cpp
Released Jan 2026 · Verified 2026-10-28

NVIDIA Parakeet

NVIDIA · Speech-To-Text

NVIDIA's STT family. parakeet-tdt-0.6b-v2 tops the HF Open ASR leaderboard for English; parakeet-tdt-0.6b-v3 adds 25-language multilingual support. Very fast on NVIDIA hardware via NeMo.

CC BY 4.0 Open weights Runs locally Mac · 8 GB+
Try on: Hugging Face (English) · Hugging Face (multilingual)
Released May 2025 · Verified 2026-10-28